© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 37115
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tank
    -0.07
     Tooth
    -0.07
     HOR
    -0.07
    .getP
    -0.07
    ῖ
    -0.06
    }$/
    -0.06
     CHO
    -0.06
    .Position
    -0.06
     indefinitely
    -0.06
    _Cl
    -0.06
    POSITIVE LOGITS
     reviewed
    0.06
    ंधन
    0.06
    schema
    0.06
    _Helper
    0.06
    스템
    0.06
    	RTHOOK
    0.06
     arsch
    0.06
    RenderingContext
    0.06
     Blizzard
    0.06
    (Parcel
    0.06
    Activations Density 0.000%

    No Known Activations